PRISP: Privacy-Safe Few-Shot Personalization via Lightweight Adaptation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915720180269056 |
|---|---|
| author | Park, Junho Kim, Dohoon Moon, Taesup |
| author_facet | Park, Junho Kim, Dohoon Moon, Taesup |
| contents | Large language model (LLM) personalization aims to adapt general-purpose models to individual users. Most existing methods, however, are developed under data-rich and resource-abundant settings, often incurring privacy risks. In contrast, realistic personalization typically occurs after deployment under (i) extremely limited user data, (ii) constrained computational resources, and (iii) strict privacy requirements. We propose PRISP, a lightweight and privacy-safe personalization framework tailored to these constraints. PRISP leverages a Text-to-LoRA hypernetwork to generate task-aware LoRA parameters from task descriptions, and enables efficient user personalization by optimizing a small subset of task-aware LoRA parameters together with minimal additional modules using few-shot user data. Experiments on a few-shot variant of the LaMP benchmark demonstrate that PRISP achieves strong overall performance compared to prior approaches, while reducing computational overhead and eliminating privacy risks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_06471 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PRISP: Privacy-Safe Few-Shot Personalization via Lightweight Adaptation Park, Junho Kim, Dohoon Moon, Taesup Computation and Language Artificial Intelligence Machine Learning Large language model (LLM) personalization aims to adapt general-purpose models to individual users. Most existing methods, however, are developed under data-rich and resource-abundant settings, often incurring privacy risks. In contrast, realistic personalization typically occurs after deployment under (i) extremely limited user data, (ii) constrained computational resources, and (iii) strict privacy requirements. We propose PRISP, a lightweight and privacy-safe personalization framework tailored to these constraints. PRISP leverages a Text-to-LoRA hypernetwork to generate task-aware LoRA parameters from task descriptions, and enables efficient user personalization by optimizing a small subset of task-aware LoRA parameters together with minimal additional modules using few-shot user data. Experiments on a few-shot variant of the LaMP benchmark demonstrate that PRISP achieves strong overall performance compared to prior approaches, while reducing computational overhead and eliminating privacy risks. |
| title | PRISP: Privacy-Safe Few-Shot Personalization via Lightweight Adaptation |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2601.06471 |